Schedule
- List
- Calendar
Tim Philipp Schäfers (TPS)
Was passiert, wenn staatliche Domains auslaufen - und plötzlich jemand anderes sie besitzt? In diesem Vortrag wird berichtet, wie mehrere ehemals offizielle, aber unregistrierte Domains deutscher Bundesministerien und Behörden erworben werden konnten - und welche Datenströme dadurch sichtbar wurden. Über Monate hinweg konnten so DNS-Anfragen aus Netzen des Bundes empfangen werden - ein erhebliches Sicherheitsrisiko. Unter anderem da es so möglich war Accounts zu übernehmen, Validierungen von E-Mailsignaturen zu manipulieren, Anfrage umzuleiten und im Extremfall Code auf Systemen auszuführen. (Keine sensiblen Daten werden veröffentlicht; der Fokus liegt auf Forschung, Aufklärung und verantwortungsvollem Umgang mit den Ergebnissen.)
Nadia Heninger, Annie Dai
We pointed a commercial-off-the-shelf satellite dish at the sky and examined all of the geostationary satellite communications visible from our vantage point. A shockingly large amount of sensitive traffic is being broadcast unencrypted, including critical infrastructure, internal corporate and government communications, private citizens’ voice calls and SMS, and consumer Internet traffic from in-flight wifi and mobile networks.
Johann Rehberger
This talk demonstrates end-to-end prompt injection exploits that compromise agentic systems. Specifically, we will discuss exploits that target computer-use and coding agents, such as Anthropic's Claude Code, GitHub Copilot, Google Jules, Devin AI, ChatGPT Operator, Amazon Q, AWS Kiro, and others. Exploits will impact confidentiality, system integrity, and the future of AI-driven automation, including remote code execution, exfiltration of sensitive information such as access tokens, and even joining Agents to traditional command and control infrastructure. Which are known as "ZombAIs", a term first coined by the presenter as well as long-term prompt injection persistence in AI coding agents. Additionally, we will explore how nation state TTPs such as ClickFix apply to Computer-Use systems and how they can trick AI systems and lead to full system compromise (AI ClickFix). Finally, we will cover current mitigation strategies and forward-looking recommendations and strategic thoughts.
Jade
"Don't roll your own crypto" is an often-repeated aphorism. It's good advice -- but then how does any cryptography get made? Writers of cryptography code like myself write code with bugs just like anyone else, so how do we take precautions against our own mistakes? In this talk, I will give a peek into the cryptographer's toolbox of advanced techniques to avoid bugs: targeted testing, model checking, mathematical proof assistants, information-flow analysis, and more. None of these techniques is a magic silver bullet, but they can help find flaws in reasoning about tricky corner cases in low-level code or prove that higher-level designs are sound, given a defined set of assumptions. We'll go over some examples and try to give a high-level feel for different workflows that create "high-assurance" code. Whether you know it or not, you use this type of cryptography code every day: in your browser, your messaging apps, and your favorite programming language standard libraries.
Mike Perry
HostileShop is a python-based tool for generating prompt injections and jailbreaks against LLM agents. I created HostileShop to see if I could use LLMs to write a framework that generates prompt injections against LLMs, by having LLMs attack other LLMs. It's LLMs all the way down. HostileShop generated prompt injections for a winning submission in OpenAI's GPT-OSS-20B RedTeam Contest. Since then, I have expanded HostileShop to generate injections for the entire LLM frontier, as well as to mutate jailbreaks to bypass prompt filters, adapt to LLM updates, and to give advice on performing injections against other agent systems. In this talk, I will give you an overview of LLM Agent hacking. I will cover LLM context window formats, LLM agents, agent vulnerability surface, and the prompting and efficiency insights that led to the success of HostileShop.
Dirk
While FPGA developers usually try to minimize the power consumption of their designs, we approached the problem from the opposite perspective: what is the maximum power consumption that can be achieved or wasted on an FPGA? Short answer: we found that it’s easy to implement oscillators running at 6 GHz that can theoretically dissipate around 20 kW on a large cloud FPGA when driving the signal to all the available resources. It is interesting to note that this power density is not very far away from that of the surface of the sun. However, such power load jump is usually not a problem as it will trigger some protection circuitry. This led us to the next question: would a localized hotspot with such power density damage the chip if we remain within the typical power envelope of a cloud FPGA (~100 W)? While we could not “fry” the chip or induce permanent errors (and we tried several variants), we did observe that a few routing wires aged to become up to 70% slower in just a few days of stressing the chip. This basically means that such an FPGA cannot be rented out to cloud users without risking timing violations. In this talk, we will present how we optimized power wasting, how we measured wire latencies with ps accuracy, how we attacked 100 FPGA cloud instances and how we can protect FPGAs against such DOS attacks.